检索结果-南通市图书馆

Adaptive Control of Output Constrained nonlinear Systems Based on nonlinear mapping 36

在线全文

学校读者我要写书评

暂无评论

Adaptive Control of Output Constrained Nonlinear Systems Bas...

Seismic-inversion method for nonlinear mapping multilevel well–seismic matching based on bidirectional long short-term memory networks

第36届中国控制会议

作者： Ningning Wang Tianping Zhang Heqing Liu Department of Automation College of Information EngineeringYangzhou University

ISBN: (纸本)9781538629185

In this paper, an adaptive dynamic surface output feedback control scheme is proposed for a class of nonlinear systems with unmodeled dynamics and output constraint. A description based on Lyapunov function for unmodeled dynamics is proposed to handle dynamic uncertainties. An one to one nonlinear mapping is introduced to solve output constrained problem. K-filters is introduced to estimate the unmeasured states. The radial basis function neural networks are utilized to approximate unknown nonlinear continuous function. It is shown that all the signals in the closed-loop system are bounded, and the output constraint is not violated. Simulation results demonstrate the effectiveness of the proposed approach.

关键词： Dynamic Surface Control Unmodeled Dynamics Output Constraint nonlinear mapping

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Applied Geophysics 2022年第2期19卷 244-257,308页

作者： Yue You-Xi Wu Jia-Wei Chen Yi-Du Shandong Provincial Key Laboratory of Deep Oil&Gas China University of Petroleum(East China)Qingdao 266580China

In this paper,the recurrent neural network structure of a bidirectional long shortterm memory network(Bi-LSTM)with special memory cells that store information is used to characterize the deep features of the variation pattern between logging and seismic data.A mapping relationship model between high-frequency logging data and low-frequency seismic data is established via nonlinear *** seismic waveform is infinitely approximated using the logging curve in the low-frequency band to obtain a nonlinear mapping model of this scale,which then stepwise approach the logging curve in the high-frequency ***,a seismic-inversion method of nonlinear mapping multilevel well–seismic matching based on the Bi-LSTM network is *** characteristic of this method is that by applying the multilevel well–seismic matching process,the seismic data are stepwise matched to the scale range that is consistent with the logging ***,the matching operator at each level can be stably obtained to effectively overcome the problems that occur in the well–seismic matching process,such as the inconsistency in the scale of two types of data,accuracy in extracting the seismic wavelet of the well-side seismic traces,and multiplicity of *** test and practical application demonstrate that this method improves the vertical resolution of inversion results,and at the same time,the boundary and the lateral characteristics of the sand body are well maintained to improve the accuracy of thin-layer sand body prediction and achieve an improved practical application effect.

关键词： bidirectional recurrent neural networks long short-term memory nonlinear mapping well–seismic matching seismic inversion

Several Results on the Number of Zeroes of nonlinear mappings on Bounded Regions

在线全文

学校读者我要写书评

暂无评论

Chinese Quarterly Journal of Mathematics 1992年第1期7卷 44-47页

作者：高堂安王则柯中山大学计算机科学系

With homotopy methods, this paper discusses the existence and the number of zeroes of nonlinear mappings on bounded regions and extends some classical theorems.

关键词： homotopy nonlinear mapping

Event-triggered adaptive finite-time control for nonlinear systems under asymmetric time-varying state constraints

在线全文

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2021年第12期22卷 1610-1624页

作者： Yan WEI Jun LUO Huaicheng YAN Yueying WANG School of Aeronautics and Astronautics Shanghai Jiao Tong UniversityShanghai 200240China School of Mechatronic Engineering and Automation Shanghai UniversityShanghai 200444China School of Information Science and Engineering East China University of Science and TechnologyShanghai 200237China

This paper investigates the issue of event-triggered adaptive finite-time state-constrained control for multi-input multi-output uncertain nonlinear *** prevent asymmetric time-varying state constraints from being violated,a tan-type nonlinear mapping is established to transform the considered system into an equivalent“non-constrained”*** employing a smooth switch function in the virtual control signals,the singularity in the traditional finite-time dynamic surface control can be *** logic systems are used to compensate for the unknown functions.A suitable event-triggering rule is introduced to determine when to transmit the control *** Lyapunov analysis,the closed-loop system is proved to be semi-globally practical finite-time stable,and the state constraints are never *** are provided to evaluate the effectiveness of the proposed approach.

关键词： Event-triggered control nonlinear mapping Adaptive fuzzy control Finite-time State constraints

Constrained docking control for shipborne UAV SideArm recovery

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2024年第5期37卷 39-59页

作者： Zikang SU Zhuolin XING Xuebing LI Chuntao LI Xinwei WANG Honglun WANG College of Automation Engineering Nanjing University of Aeronautics and AstronauticsNanjing 211106China School of Engineering and Materials Science Queen Mary University of LondonLondon E14NSUK School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100191China

In this work,we sought to investigate constrained docking control during shipborne SideArm recovery of an Unmanned Aerial Vehicle(UAV)under preassigned safe docking constraints,rough ocean environments,and different initial *** aim was to solve the UAV tracking-lag problem that manifests when attempting to dock with a rapidly moving SideArm and to improve the accuracy and rapidity of ***,together with the formulations of the shipborne SideArm system and environmental airflows,the affine nonlinear dynamics of the hook was established to reduce tracking ***,echo state network approximators with good approximation capacity and low computational consumption were designed to accurately approximate the UAV’s unknown nonlinear *** feedforward compensation provided by these approximators,a nonlinear-mapping-based constrained docking control law was developed for shipborne SideArm recovery of *** approach to controlling the docking trajectory and the forward docking speed of the UAV can achieve rapid and exact docking with a moving SideArm,without violating the preassigned safe docking-constraint *** under different docking scenarios were used to validate the effectiveness and advantages of the proposed docking-control algorithm.

关键词： SideArm recovery Unmanned aerial vehicle Docking control nonlinear mapping Echo state network

VARIATIONS IN THE TELECONNECTION INTENSITY INDICES AND THEIR REMOTE RESPONSE TO THE EL NINO EVENTS IN THE NORTHERN HEMISPHERE

在线全文

学校读者我要写书评

暂无评论

Acta meteorologica Sinica 1992年第4期6卷 433-445页

作者：朱乾根施能 Nanjing Institute of Meteorology Nanjing 210044

In this study,the monthly and seasonal teleconnection intensity indices of the Pacific/North American(PNA), Western Atlantic(WA),Western Pacific(WP),Eastern Atlantic(EA)and Eurasian(EU)patterns for the period from 1951 through 1990 are *** this basis,their climatic variations and the relationship between the five teleconnection intensity indices and the El Nino events are *** is noted that when El Nino is at its mature stage (winter),the weak WP pattern is mainly characteristic of the circulation and the strong PNA pattern is the *** summer when El Nino occurs and develops,the strong EU,weak WP and weak WA patterns are the main characteris- tics without the PNA circulation ***,by the nonlinear mapping method a nonlinear mapping diagram is established for diagnosing El Nino using three summer teleeonuection intensity indices and May and August Southern Oscillation Indices(SOIs).Thus,the El Nino phenomenon occurring in 1991 is ***,the winter atmos- pheric circulation of the 1991/1992 El Nino is found to be the weak WP pattern and the PNA pattern is also weak.

关键词： teleconnection pattern El Nino nonlinear mapping remote response

STUDY ON MIXED MODEL OF NEURAL NETWORK FOR FARMLAND FLOOD/DROUGHT PREDICTION

在线全文

学校读者我要写书评

暂无评论

Acta meteorologica Sinica 1997年第3期11卷 364-373页

作者：金龙罗莹郭光林振山 Jiangsu Meteorological Institute Nanjing 210008 Jiangsu Institute of Climate Application Nanjing 210009 Nanjing Institute of Meteorology Nanjing 210044 Department of Atmospheric Sciences Nanjing UniversityNanjing 210093

The paper concerns a flood/drought prediction model involving the continuation of time series of a predictand and the physical factors influencing the change of *** is made to construct the model by the neural network scheme for the nonlinear mapping relation based on multi-input and single *** model is found of steadily higher predictive accuracy by testing the output from one and multiple stepwise predictions against observations and comparing the results to those from a traditional statistical model.

关键词： flood/drought prediction mixed model nonlinear mapping soil humidity neural network

Multi-label Learning via Supervised Autoencoder

在线全文

学校读者我要写书评

暂无评论

Multi-label Learning via Supervised Autoencoder

The Prediction Model of Coal Mine Disaster Based on BP Algorithm

第37届中国控制会议

作者： Siming Lian Jianwei Liu Runkun Lu Xionglin Luo Department of Automation China University of Petroleum Beijing Campus （CUP）

Multi-label learning has been applied in various areas. One crucial research issue in multi-label learning is how to find a complex nonlinear mapping between instances and multi-label such that the instances with unknown labels can be predicted with the mapping. In this paper, we propose a multi-label learning method based on supervised deep autoencoder, and study the effects of the various combinations of the constraints of hidden layers and output layers. In the output layer, the sum-square error of the true labels and estimating labels is minimized through backpropagation-through-time learning algorithm. Extensive experiments conducted on eight real-world datasets demonstrate the effectiveness of our proposed method compared with several state-of-art baseline methods.

关键词： Multi-Label Learning nonlinear mapping Supervised Autoencoder

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

The Prediction Model of Coal Mine Disaster Based on BP Algor...